Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3724 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1429467 (The Pile)

Max Activating Token Index: 272

Text #1

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1164188 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6205. Min Act: -0.0000

Data Index: 921361 (The Pile)

Max Activating Token Index: 720

Text #3

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6098. Min Act: -0.0000

Data Index: 297980 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1895173 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1776343 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1763394 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1363647 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5693. Min Act: -0.0000

Data Index: 456919 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6057. Min Act: -0.0000

Data Index: 927754 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5765. Min Act: -0.0000

Data Index: 604041 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5472. Min Act: 0.0000

Data Index: 1598501 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5764. Min Act: 0.0000

Data Index: 1982613 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1514973 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5267. Min Act: -0.0000

Data Index: 91588 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5350. Min Act: -0.0000

Data Index: 879242 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5334. Min Act: -0.0000

Data Index: 38294 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5186. Min Act: -0.0000

Data Index: 864889 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1349822 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1304203 (The Pile)

Max Activating Token Index: 179